Austin, TX

• •Developed and mocked STM32 FreeRTOS firmware, adding and testing features, for new touchscreen interface on Toshiba MVDs. Created automated testing infrastructure from scratch on x64 and ARM architectures (C, Python, Bash, Ruby). Built secure production CI/CD pipeline validating 10,000+ params via unit, integration, and HIL tests to cut QA time by 60%.
• •Optimized RTOS task priorities and DMA scheduling, reducing TouchGFX CPU overhead from 41% to 18%, achieving 25% total system CPU reduction, and eliminating all timing violations to correct issues revealed by my new HIL tests. (C, C++).
• •Engineered a RAG based AI agent using Azure Copilot and OCR for detecting defects in CAD drawings with 94% precision.

San Marcos, TX

• •Developed cross-modal distillation pipeline (video to IMU sensors) and personally trained custom multimodal transformers for fall detection under Dr. Anne Ngu. Deployed to edge devices (phones, wearables) with 92% F1 score in real time.
• •Built distributed Ray Train pipeline w/ automated validation/testing on edge devices achieving 600% speedup, added efficient attention mechanisms increasing F1 +4%, tested DSP + sensor fusion algorithms to align modalities increasing F1 +5%.
• •Refactored multimodal PyTorch / TensorFlow transformer models to edge via TFlite and ONNX using INT8 quantization + mixed-precision training, achieving 2-3x battery life w/ sub-1% accuracy loss allowing for on device inference (Python).
• •Refactored full-stack Android app (Java/Kotlin) to support ONNX, AWS S3, and DynamoDB for sensor analytics. Built secure distributed data pipeline with Kafka / Spark for async server-side inference and fault tolerant processing.

San Marcos, TX

• •Collaborated with research team funded by Texas State C.A.D.S to fine-tune Vision Transformer and MASK R-CNN models on distributed GPU SLURM cluster with Nvidia A100 GPUs. Created custom dataset achieving 98% precision for defect detection.
• •Built production REST API using Python FastAPI, PostgreSQL, and Docker for deployment on Huggingface; implemented server side async request handling and batch processing to handle concurrent requests from React Native mobile app.
• •Accelerated inference via layer fusion and ONNX to TensorRT engine conversion; reducing latency and cloud costs by 40%.
• •Built automated computer vision annotation pipeline leveraging Detectron2 and CVAT for model-assisted labeling with MLOps pipeline, implemented active learning loop prioritizing low-confidence samples, reducing manual labeling hours by 80%.